Bandwidth prediction based on nu-support vector regression and parallel hybrid particle swarm optimization

Cheng, Xiaochun ORCID: https://orcid.org/0000-0003-0371-9646, Che, Xilong and Hu, Liang (2010) Bandwidth prediction based on nu-support vector regression and parallel hybrid particle swarm optimization. International Journal of Computational Intelligence Systems, 3 (1) . pp. 70-83. ISSN 1875-6891 (doi:10.2991/ijcis.2010.3.1.7)

Abstract

This paper addresses the problem of generating multi-step-ahead bandwidth prediction. Variation of bandwidth is modeled as a Nu-Support Vector Regression (Nu-SVR) procedure. A parallel procedure is proposed to hybridize constant and binary Particle Swarm Optimization (PSO) together for optimizing feature selection and hyper-parameter selection. Experimental results on benchmark data set show that the Nu-SVR model optimized achieves better accuracy than BP neural network and SVR without optimization. As a combination of feature selection and hyper-parameter selection, parallel hybrid PSO achieves better convergence performance than individual ones, and it can improve the accuracy of prediction model efficiently.
(as on publishers website)

Item Type: Article
Keywords (uncontrolled): bandwidth prediction, hyper-parameter selection, feature selection, nu-support vector regression, parallel hybrid particle swarm optimization,
Research Areas: A. > School of Science and Technology
A. > School of Science and Technology > Computer Science > Artificial Intelligence group
A. > School of Science and Technology > Computer and Communications Engineering
Item ID: 11130
Useful Links:
Depositing User: Teddy ~
Date Deposited: 03 Jul 2013 09:57
Last Modified: 30 Oct 2019 21:04
URI: https://eprints.mdx.ac.uk/id/eprint/11130

Actions (login required)

Edit Item Edit Item